← back to catalog · registered 2026-08-22 13:56

RichardErkhov/aspirina765_-_Daredevil-8B-abliterated-gguf

RichardErkhov 8B GGUF 8K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/RichardErkhov%2Faspirina765_-_Daredevil-8B-abliterated-gguf"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 398
  • author_summary 257 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
398
234 last 30d - active
Likes
0
Model age
2.1y ago
created 2024-08-23
Downloads over time
Now435→from219↑99%
0320640960219 on Aug 21, 2024435 on Oct 11873 on Jan 7Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 21, 2024 → Oct 11 · 151 snapshots · spans 781 days

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
45.4 GB
Files
13
Quantizations
7
Registered
2026-08-22 13:56
Last updated on HF
2024-08-24 00:22

Files by quantization

IQ4 2 files 8.56 GB
Daredevil-8B-abliterated.IQ4_NL.gguf 4.38 GB 9d729b83 download
Daredevil-8B-abliterated.IQ4_XS.gguf 4.18 GB f9d04fe9 download
Q4_K 1 file 4.37 GB
Daredevil-8B-abliterated.Q4_K_S.gguf 4.37 GB d2a9b5bb download
Q4 1 file 4.34 GB
Daredevil-8B-abliterated.Q4_0.gguf 4.34 GB ccdea433 download
Q3_K 4 files 14.9 GB
Daredevil-8B-abliterated.Q3_K_L.gguf 4.03 GB 03f99892 download
Daredevil-8B-abliterated.Q3_K.gguf 3.74 GB 59241a1b download
Daredevil-8B-abliterated.Q3_K_M.gguf 3.74 GB 59241a1b download
Daredevil-8B-abliterated.Q3_K_S.gguf 3.41 GB 6cb8b6f7 download
IQ3 3 files 10.2 GB
Daredevil-8B-abliterated.IQ3_M.gguf 3.52 GB 02773e20 download
Daredevil-8B-abliterated.IQ3_S.gguf 3.43 GB 28d5621a download
Daredevil-8B-abliterated.IQ3_XS.gguf 3.28 GB 45261fd3 download
Q2_K 1 file 2.96 GB
Daredevil-8B-abliterated.Q2_K.gguf 2.96 GB b10e421d download
Auxiliary files 1 file 2.33 KB
.gitattributes 2.33 KB 1a27bd25 download

README

The author did not publish a README.

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration